Method for extracting motor imagery electroencephalogram signal feature based on non-linear dynamics

Abstract

The invention discloses a method for extracting the motor imagery electroencephalogram signal feature based on non-linear dynamics, and solves the problem of low and instable classification accuracy due to low signal-to-noise ratio of a motor imagery electroencephalogram signal possibly caused in a practical application environment. The method comprises the concrete steps as follows: (1) acquiring data; (2) carrying out spatial filtering; (3) carrying out baseline correction; (4) carrying out band-pass filtering; (5) carrying feature extraction; and (6) classifying. The method has the advantages of effectively guaranteeing stable classification accuracy of the electroencephalogram signal and effectively providing better real-time performance.

Description

technical field [0001] The invention belongs to the field of information technology, and further relates to a method for extracting features of motor imagery EEG signals based on nonlinear dynamics using a brain-computer interface (Brain-Computer Interface, BCI) system in the field of life sciences. The invention is used to extract the features of motor imagery EEG signals, classify the features through a classifier, realize the discrimination of unilateral finger motor imagery, and finally can be applied to BCI online systems for motor imagery such as wheelchairs and mice, thereby improving the quality of people with disabilities. The ability to communicate with the outside world. Background technique [0002] When preparing and performing unilateral finger motor imagery, the functional connectivity of people's cerebral cortex changes, which leads to the weakening of EEG signal energy in the motor sensory area mu and beta rhythm of the contralateral brain, while the motor s...

AI Technical Summary

Problems solved by technology

Although the common spatial pattern method can obtain a good accuracy rate for the classification of motor imagery EEG signals with high signal-to-noise ratio, the disadvantage of this patented technology is that in practical applications, there is usually no ideal data in the laboratory. Acquisition environment, so the motor imagery EEG signals collected in practical applications often contain a lot of noise compared with the data collected in the laboratory, and the signal-to-noise ratio is low

Using the common space mode method to analyze and process the motor imagery EEG signals collected in practical applications has a low accuracy rate, poor stability, and a large amount of algorithm calculation, which is not conducive to the promotion of practical applications

Images